MCP AI Agent Server

Brings Cline messages into an AI agent system session with managed assistants via the MCP.

typescript

0

GitHub Stars

typescript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "singularitybridge-mcp-ai-agent-server": {
      "command": "npx",
      "args": [
        "@avi/mcp-ai-agent-server"
      ],
      "env": {
        "AI_AGENT_API_KEY": "your-api-key-here",
        "AI_AGENT_BASE_URL": "http://localhost:3000"
      }
    }
  }
}

You run this MCP server to connect Cline clients to an AI agent system, enabling you to send messages in sessions, manage sessions, and switch assistants on the fly. It provides a simple, consistent way to interact with AI agents through the Model Context Protocol, keeping your workflow focused and reliable.

How to use

You interact with this MCP server through an MCP client. Start or connect to the server, then begin a session, send messages, and manage the conversation by adjusting the active assistant when needed.

Typical usage patterns include starting a session, sending a message within that session, and optionally changing the assistant to tailor responses. You can also clear the current session to start fresh when a new topic emerges.

How to install

Prerequisites: ensure Node.js and npm are installed on your system.

# Install the MCP AI Agent Server globally (recommended)
npm install -g @avi/mcp-ai-agent-server

# Or run without installing (uses npx)
npx @avi/mcp-ai-agent-server

Configuration and environment

Configure the MCP client to connect to this server using the following MCP settings. The server runs via a standard npx invocation and requires an API key and a base URL for the AI agent service.

{
  "mcpServers": {
    "ai-agent-mcp": {
      "command": "npx",
      "args": ["@avi/mcp-ai-agent-server"],
      "env": {
        "AI_AGENT_API_KEY": "your-api-key-here",
        "AI_AGENT_BASE_URL": "http://localhost:3000"
      }
    }
  }
}

Environment variables

Two environment variables are required to run the MCP AI Agent Server. The API key authorizes access to the AI agent service, and the base URL points to the AI agent endpoint.

AI_AGENT_API_KEY: your-api-key-here
AI_AGENT_BASE_URL: http://localhost:3000

Available tools

send_message

Send a message in an active session with optional attachments to continue the conversation with the AI agent.

get_session

Retrieve the current session or create a new one if none exists, enabling you to group messages.

clear_session

Clear the current session and start a new one to begin a fresh conversation context.

get_assistants

Fetch the list of available assistants you can switch to for the current or a new session.

change_assistant

Change the active assistant for a session by specifying the session and the new assistant ID.